Semisupervised autoencoder for sentiment analysis
(57) ABSTRACT A method of modelling data, comprising: training an objec tive function of a
linear classifier, based on a set of labeled data, to derive a set of classifier weights; defining …
linear classifier, based on a set of labeled data, to derive a set of classifier weights; defining …
System and method for combining speech recognition outputs from a plurality of domain-specific speech recognizers via machine learning
M Gilbert, S Bangalore, P Haffner, R Bell - US Patent 8,812,321, 2014 - Google Patents
Disclosed herein are systems, methods and non-transitory computer-readable media for
performing speech recognition across different applications or environments without model …
performing speech recognition across different applications or environments without model …
Wake word evaluation
SW Salvador, JP Lilly, FV Weber, JP Adams… - US Patent …, 2016 - Google Patents
BACKGROUND Homes are becoming more wired and connected with the proliferation of
computing devices such as desktops, tablets, entertainment systems, and portable …
computing devices such as desktops, tablets, entertainment systems, and portable …
Realtime acoustic adaptation using stability measures
X Lei, P Aleksic - US Patent 8,515,750, 2013 - Google Patents
US8515750B1 - Realtime acoustic adaptation using stability measures - Google Patents
US8515750B1 - Realtime acoustic adaptation using stability measures - Google Patents …
US8515750B1 - Realtime acoustic adaptation using stability measures - Google Patents …
Processing sequences using convolutional neural networks
AGA van den Oord, SEL Dieleman… - US Patent …, 2021 - Google Patents
Methods, systems, and apparatus, including computer programs encoded on computer
storage media, for processing sequences using convolutional neural networks. One of the …
storage media, for processing sequences using convolutional neural networks. One of the …
Insight and algorithmic clustering for automated synthesis
G Swamy - US Patent 9,336,302, 2016 - Google Patents
(52) US Cl. CPC...... G06F 17/3071 (2013.01); G06F 17/30306 (2013.01); G06F 17/30648
(2013.01) A decision Support system and method, which receives user inputs comprising: at …
(2013.01) A decision Support system and method, which receives user inputs comprising: at …
Method and apparatus for automatically determining speaker characteristics for speech-directed advertising or other enhancement of speech-controlled devices or …
H Printz, V Gulati - US Patent 8,793,127, 2014 - Google Patents
In addition to conveying primary information, human speech also conveys information
concerning the speaker's gender, age, socioeconomic status, accent, language spoken …
concerning the speaker's gender, age, socioeconomic status, accent, language spoken …
System and method for decoding speech
The system and method for speech decoding in speech rec ognition systems provides
decoding for speech variants com mon to Such languages. These variants include within …
decoding for speech variants com mon to Such languages. These variants include within …
Gift card recognition using a camera
AW Kraft - US Patent 9,430,766, 2016 - Google Patents
a camera or otherwise receive an image of that gift card. The computing device can be
configured to recognize codes, Such as digit claim codes, of the gift card by using one or …
configured to recognize codes, Such as digit claim codes, of the gift card by using one or …
Grapheme-to-phoneme conversion using acoustic data
X Li, AJR Gunawardana, A Acero - US Patent 7,991,615, 2011 - Google Patents
BACKGROUND Grapheme-to-phoneme (G2P) conversion is directed towards automatically
generating pronunciations (or pho neme sequences) from word spellings (or grapheme …
generating pronunciations (or pho neme sequences) from word spellings (or grapheme …